INDEX

Explanations

phrases that indicate a need for significant change or improvement

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÙĪØ¯

-0.14

urge

-0.14

insky

-0.14

à¸µà¹Ĥà¸Ń

-0.14

ctors

-0.14

roy

-0.14

åľŃ

-0.14

chten

-0.13

ourcing

-0.13

urance

-0.13

POSITIVE LOGITS

Å¡ov

0.14

meter

0.14

å¨ĺ

0.14

tel

0.14

orman

0.14

IFF

0.14

emme

0.14

 station

0.13

Portable

0.13

 adjunct

0.13

Activations Density 0.021%

phrases that indicate a need for significant change or improvement

No Comments

No Known Activations